AliceArchiveX / blue-fat-fish Star 5 Code Issues Pull requests 通过权重修改,让开源模型讯飞星火Spark-X2.5-4B彻底相信自己是一只傲娇的AI鲸鱼 roleplay deepseek residual-stream frozen-backbone behavioral-evaluation polysemanticity spark-x2-5 fatfish Updated Oct 12, 2026 Python
EEthanShi / awesome-superposition Star 2 Code Issues Pull requests A curated reading list on feature superposition in neural networks, plus a daily arXiv feed on superposition and mechanistic interpretability. machine-learning deep-learning awesome-list arxiv superposition sparse-autoencoders interpretability paper-list mechanistic-interpretability polysemanticity Updated Nov 19, 2026 JavaScript
coeiico / sardines-mlp Star 0 Code Issues Pull requests Reproducing toy models of superposition: how a network stores more features than it has dimensions. machine-learning deep-learning pytorch superposition features reproduction interpretability toy-models mechanistic-interpretability polysemanticity Updated Oct 31, 2026 Python
stanleyngugi / taming_polysemanticity Star 0 Code Issues Pull requests Toy-model experiments on how training configurations affect feature-entanglement proxies in neural representations. pytorch sparse-autoencoders toy-models mechanistic-interpretability polysemanticity Updated Sep 10, 2026 Python